AI Summary & Key Takeaways
AI InsightGenerally, the results showed that the SVR had less uncertainty in CO prediction than theANN and ANFIS models.
📌 3 Key Takeaways
Özet
Air pollution modeling is always along with uncertainties which results in improper decision making andaffects the health of the people exposed to the pollution. Therefore, the determination of model uncertaintycan improve air pollution control strategies especially in critical conditions. This study aims todevelop an appropriate methodology for determination of uncertainty in support vector regression (SVR)as a well-known modeling approach in atmospheric science. The methodology is based on running SVRmodel many times using different calibration datasets. The robustness of the proposed methodology waschecked to predict the next day carbon monoxide (CO) concentrations in Tehran metropolitan. Thereafter,a comparison was carried out between the results of the present study and another research onuncertainty determination of adaptive neuro-fuzzy inference system (ANFIS) and artificial neuralnetwork (ANN). Generally, the results showed that the SVR had less uncertainty in CO prediction than theANN and ANFIS models. Moreover, repetition of SVR runs with different calibration datasets resulted indifferent SVR responses. Different SVR responses provided the required information to determine theband of uncertainty for predictions, using specific lower and upper percentiles. Besides, it is found thatmore than 75% and 78% of SVR predictions are located in the band of uncertainty determined by 2.5the97.5th and 0.5the99th percentiles, respectively.